ycliper

Популярное

Музыка Кино и Анимация Автомобили Животные Спорт Путешествия Игры Юмор

Интересные видео

2025 Сериалы Трейлеры Новости Как сделать Видеоуроки Diy своими руками

Топ запросов

смотреть а4 schoolboy runaway турецкий сериал смотреть мультфильмы эдисон
Скачать

Corey J. Nolet, Vivek Narang – cuVS and Lucene: GPU-based Vector Search

Автор: Plain Schwarz

Загружено: 2024-06-10

Просмотров: 754

Описание: By 2025, it is believed that 80% of all data will be unstructured. Meanwhile, modern advances in large language models and generative AI have acted as a catalyst for the use of vector embeddings, which are impacting nearly every industry. Vector search is growing in popularity and, thanks to these advances, the need for efficient and scalable semantic search is becoming more evident. GPUs have become synonymous with AI over the past decade, but even more intriguing is the advancement of software capabilities that can leverage GPUs to accelerate more general-purpose data processing workloads like vector search.

cuVS, from Nvidia [1], is a CUDA-based library containing state of the art implementations of several algorithms for approximate nearest neighbors and clustering on the GPU. Apache Lucene [2] is an open-source search library that is at the core of popular search engines like MongoDB, Elasticsearch, OpenSearch and Apache Solr.

This talk will have two main parts, 1) Introduction to Nvidia’s cuVS library, its history, approximate nearest neighbor search algorithm types, their implementations and comparison, the novel graph-based CAGRA algorithm, and the cuVS future roadmap. 2) Integration of cuVS into Apache Lucene to power GPU accelerated vector search, the motivations, challenges, the roadmap associated with this integration, and potential future directions for turbo-charging Lucene on the GPU.

We will provide benchmarks and lessons we've learned along the way, and hope that this will spark a new trend where GPUs can be used to accelerate other compute-heavy search, analytics and database tasks in the future.

[1] - cuVS, https://github.com/rapidsai/cuvs, was formerly part of RAFT, https://github.com/rapidsai/raft
[2] - https://github.com/apache/lucene

Speakers: Corey J. Nolet, Vivek Narang

More: https://2024.berlinbuzzwords.de/sessi...

###

Follow us on Social Media and join the Community!
Mastodon: https://floss.social/@berlinbuzzwords
LinkedIn:   / berlin-buzzwords  
Instagram:   / berlinbuzzwords  

Website: https://2024.berlinbuzzwords.de

Berlin Buzzwords is an event by Plain Schwarz – https://plainschwarz.com

Не удается загрузить Youtube-плеер. Проверьте блокировку Youtube в вашей сети.
Повторяем попытку...
Corey J. Nolet, Vivek Narang – cuVS and Lucene: GPU-based Vector Search

Поделиться в:

Доступные форматы для скачивания:

Скачать видео

  • Информация по загрузке:

Скачать аудио

Похожие видео

Yingjun Wu - S3 as the state store for stream processing systems

Yingjun Wu - S3 as the state store for stream processing systems

Lucian Precup – Apache Lucene: From Text Indexing to Artificial Intelligence

Lucian Precup – Apache Lucene: From Text Indexing to Artificial Intelligence

Программирование графических процессоров с использованием языка шейдинга Metal.

Программирование графических процессоров с использованием языка шейдинга Metal.

GPU-Accelerated HNSW Vector Indexing - Ivan Pleshkov | Vector Space Talks #023

GPU-Accelerated HNSW Vector Indexing - Ivan Pleshkov | Vector Space Talks #023

Alixia Rutayisire - The Proxy Warfare: Unmasking Russian and Chinese externalized Cyber Capabilities

Alixia Rutayisire - The Proxy Warfare: Unmasking Russian and Chinese externalized Cyber Capabilities

Latest breakthroughs in vector search for Elasticsearch and Lucene: ElasticON AI

Latest breakthroughs in vector search for Elasticsearch and Lucene: ElasticON AI

Haystack US 2024

Haystack US 2024

CPU против GPU | Программирование GPU | Эпизод 1

CPU против GPU | Программирование GPU | Эпизод 1

NeMo: набор инструментов с открытым исходным кодом для диалогового искусственного интеллекта – Ел...

NeMo: набор инструментов с открытым исходным кодом для диалогового искусственного интеллекта – Ел...

GPU Acceleration in Vector Databases

GPU Acceleration in Vector Databases

Introduction to Apache Lucene & Elasticsearch

Introduction to Apache Lucene & Elasticsearch

Frank Munz – Analysing Public Kafka Data from NASA Satellites #bbuzz

Frank Munz – Analysing Public Kafka Data from NASA Satellites #bbuzz

Stanford CS224W Machine Learning with Graphs I Jure Leskovec

Stanford CS224W Machine Learning with Graphs I Jure Leskovec

Haystack US 2024 - Lucian Precup: Apache Lucene: From Text Indexing to Artificial Intelligence

Haystack US 2024 - Lucian Precup: Apache Lucene: From Text Indexing to Artificial Intelligence

Почему Андрей Карпати чувствует себя

Почему Андрей Карпати чувствует себя "отстающим" (и что это значит для вашей карьеры)

Mongo DB v1 4k+ Boot Dev

Mongo DB v1 4k+ Boot Dev

Kevin Liang – Performance Tuning Apache Solr for Dense Vectors #bbuzz

Kevin Liang – Performance Tuning Apache Solr for Dense Vectors #bbuzz

Драйверы Nvidia становятся с открытым исходным кодом

Драйверы Nvidia становятся с открытым исходным кодом

Vergecast live at CES 2026 | The Vergecast

Vergecast live at CES 2026 | The Vergecast

Nvidia CUDA in 100 Seconds

Nvidia CUDA in 100 Seconds

© 2025 ycliper. Все права защищены.



  • Контакты
  • О нас
  • Политика конфиденциальности



Контакты для правообладателей: [email protected]